A Methodology Based on Computer Vision and Machine Learning for Motion Detection and Analysis During Physiotherapy Exercises

• Grant number: 22/15472-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2023
• End date: February 29, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Paulo Sergio Silva Rodrigues
• Grantee: Gustavo Garcia Bagio
• Host Institution: Centro Universitário FEI (UNIFEI). Campus de São Bernardo do Campo. São Bernardo do Campo , SP, Brazil

Abstract

Physical rehabilitation techniques, after or during the treatment of clinical pathologies, are one of the most challenging steps for the medical structure and patients and families. In continental countries like Brazil, the need for remote monitoring of this type of treatment is not just a humanitarian issue but also a strategic and economic issue. However, equipment and medical consultation during the exercises still have high costs. With the advancement of Computer Vision and Machine Learning techniques, some relatively less expensive computational alternatives have been proposed in the literature. However, the follow-up of patients during physical therapy exercises with the help of artificial intelligence by a health professional, especially from the capture of visual signals, still needs to be explored in the scientific-technological literature. This work presents the development of a system based on an RBG camera for machine learning training to track people's body joints in real-time, to optimize the results of physiotherapy sessions.